external benchmark
Public Benefits Bench v1.1 leaderboard
Vals Public Benefits Bench v1.1. Every model the catalog carries a published Public Benefits Bench v1.1 value for, ranked by that value.
Categoryexternal
MeasureAccuracy score
TasksSNAP public-benefits navigation tasks
DifficultyPublic-benefits policy navigation
Published byPublic Benefits Bench v1.1
Can AI help people navigate SNAP benefits?
No model in the catalog has a published Public Benefits Bench v1.1 score.
The benchmark is defined by Public Benefits Bench v1.1, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.